© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2594
    Prev
    Next
    INDEX
    Explanations

    knowledge and principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦ详ç»Ĩ
    -0.08
     thereafter
    -0.08
    adah
    -0.08
     bát
    -0.08
    ä¸īé¤IJ
    -0.08
    apati
    -0.08
    á»Ŀ
    -0.08
     Disclaimer
    -0.08
    æĢĿæĥ³å·¥ä½ľ
    -0.07
    çļĦæīĢæľīæĸĩåŃĹ
    -0.07
    POSITIVE LOGITS
    常è¯Ĩ
    0.12
    åŁºæľ¬æ¦Ĥ念
    0.09
    çŁ¥è¯ĨçĤ¹
    0.09
    åŁºæľ¬çŁ¥è¯Ĩ
    0.09
    è®°ä½ı
    0.09
    çŁ¥è¯Ĩ
    0.08
     correctly
    0.08
     basics
    0.08
    æŃ£ç¡®
    0.08
    缸åħ³çŁ¥è¯Ĩ
    0.08
    Activations Density 0.010%

    No Known Activations